Project Start Date:
Project Objectives and Scope
It was demonstrated how a compromised avionic computer may launch a cyber-attack against other computers connected to avionics buses. The main objectives of this project are: (i) extensive study of the attacks that can be performed against avionics systems and (ii) development of solutions based on deep learning techniques for detecting and preventing cyber attacks and anomaly behaviors.
The main challenge is to establish where to place the analyzer in order to effectively and timely detect cyber-attacks and anomalous behaviors. Additionally, the technology that is going to be introduced in the avionic platform should not have negative impact on the computer’s communication and operations.
In this project we research novel detection algorithms based on data-driven approach, supervised, semi-supervised and unsupervised learning approaches, and state-of-the-art deep learning approaches. We research new time series machine learning algorithms that can model the system over time. Time series machine learning algorithms, in particular, Recurrent Neural Networks, have the ability to model what they have seen in the past. This concept would be useful for the detection of these attacks having low profiles with long-term execution.